AI 智能体论文趋势 2023–2026

主要结论

• AI 智能体论文从 2023 年的 170 篇增长到 2026 年的 1,983 篇，三年间扩大到约 12 倍。
• NeurIPS 是发AI 智能体论文最多的会议，2023–2026 年共 1,317 篇，占四个会议总量的 40%。
• 交叉方向里涨得最快的是大模型基准：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 116 篇。
• 在「前沿系统」的 4 个主题里，它的 2026 年论文数排第 2；同组增长最快的世界模型是 11 倍，AI 智能体是 12 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026$\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control
• ICML 2026$\tau$-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge
• ICLR 2026A Benchmark for Deep Information Synthesis
• CVPR 20263D-VCD Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive
• NeurIPS 20254KAgent: Agentic Any Image to 4K Super-Resolution
• ICML 2025A Unified Approach to Routing and Cascading for LLMs
• ICLR 2025A Generalist Hanabi Agent
• CVPR 2025Collaborative Tree Search for Enhancing Embodied Multi-Agent Collaboration
• NeurIPS 2024AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making
• ICML 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
• ICLR 2024A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
• CVPR 2024Density-Adaptive Model Based on Motif Matrix for Multi-Agent Trajectory Prediction
• NeurIPS 2023AdaPlanner: Adaptive Planning from Feedback with Language Models
• ICML 2023A Game-Theoretic Framework for Managing Risk in Multi-Agent Systems
• ICLR 2023Achieving Near-Optimal Individual Regret & Low Communications in Multi-Agent Bandits
• CVPR 2023Behavioral Analysis of Vision-and-Language Navigation Agents
• NeurIPS 20262-Step Agent: How a Bayesian Decision Maker Learns from AI-Decision Support
• ICML 2026$\tau$-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domains
• ICLR 2026A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice Experiments
• CVPR 2026A Multi-Agent Perception-Action Alliance for Efficient Long Video Reasoning

全部AI 智能体论文

共 817 篇，第 2 / 17 页

51. ICLR 2026Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE
52. ICLR 2026Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts
53. ICLR 2026Beyond URLs: Metadata Diversity and Position for Efficient LLM Pretraining
54. ICLR 2026BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models
55. ICLR 2026BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation via Lens of Dynamic Interactions
56. ICLR 2026Breaking Agent Backbones: Evaluating the Security of Backbone LLMs in AI Agents
57. ICLR 2026Breaking and Fixing Defenses Against Control Flow Hijacking in Multi-Agent Systems
58. ICLR 2026BRIDGE: Bi-level Reinforcement Learning for Dynamic Group Structure in Coalition Formation Games
59. ICLR 2026Building a Foundational Guardrail for General Agentic Systems via Synthetic Data
60. ICLR 2026Cache-to-Cache: Direct Semantic Communication Between Large Language Models
61. ICLR 2026Can Language Models Discover Scaling Laws?
62. ICLR 2026Cancer-Myth: Evaluating Large Language Models on Patient Questions with False Presuppositions
63. ICLR 2026CARD: Towards Conditional Design of Multi-agent Topological Structures
64. ICLR 2026CARE: Towards Clinical Accountability in Multi-Modal Medical Reasoning with an Evidence-Grounded Agentic Framework
65. ICLR 2026Catalog-Native LLM: Speaking Item-ID dialect with Less Entanglement for Recommendation
66. ICLR 2026CellAgent: LLM-Driven Multi-Agent Framework for Natural Language-Based Single-Cell Analysis
67. ICLR 2026CellDuality: Unlocking Biological Reasoning in LLMs with Self-Supervised RLVR
68. ICLR 2026ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents
69. ICLR 2026ChinaTravel: An Open-Ended Travel Planning Benchmark with Compositional Constraint Validation for Language Agents
70. ICLR 2026CLAUSE: Agentic Neuro-Symbolic Knowledge Graph Reasoning via Dynamic Learnable Context Engineering
71. ICLR 2026CoAct-1: Computer-using Multi-agent System with Coding Actions
72. ICLR 2026CoDA: Agentic Systems for Collaborative Data Visualization
73. ICLR 2026Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration
74. ICLR 2026CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Control
75. ICLR 2026CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards
76. ICLR 2026CoMind: Towards Community-Driven Agents for Machine Learning Engineering
77. ICLR 2026Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing
78. ICLR 2026Completing Missing Annotation: Multi-Agent Debate for Accurate and Scalable Relevant Assessment for IR Benchmarks
79. ICLR 2026Computer Agent Arena: Toward Human-Centric Evaluation and Analysis of Computer-Use Agents
80. ICLR 2026ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents
81. ICLR 2026CoNavBench: Collaborative Long-Horizon Vision-Language Navigation Benchmark
82. ICLR 2026Context Learning for Multi-Agent Discussion
83. ICLR 2026ContextNav: Towards Agentic Multimodal In-Context Learning
84. ICLR 2026Continual Low-Rank Adapters for LLM-based Generative Recommender Systems
85. ICLR 2026Continuous-Time Value Iteration for Multi-Agent Reinforcement Learning
86. ICLR 2026Control Tax: The Price of Keeping AI in Check
87. ICLR 2026Correlated Policy Optimization in Multi-Agent Subteams
88. ICLR 2026CP-Agent: Context‑Aware Multimodal Reasoning for Cellular Morphological Profiling under Chemical Perturbations
89. ICLR 2026Credit-Budgeted ICPC-Style Coding: When LLM Agents Must Pay for Every Decision
90. ICLR 2026CubeBench: Diagnosing Interactive, Long-Horizon Physical Intelligence under Partial Observations
91. ICLR 2026Cyber-Zero: Training Cybersecurity Agents without Runtime
92. ICLR 2026CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale
93. ICLR 2026DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle
94. ICLR 2026DAMR: Efficient and Adaptive Context-Aware Knowledge Graph Question Answering with LLM-Guided MCTS
95. ICLR 2026DARE-bench: Evaluating Modeling and Instruction Fidelity of LLMs in Data Science
96. ICLR 2026Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents
97. ICLR 2026DASH: Deterministic Attention Scheduling for High-throughput Reproducible LLM Training
98. ICLR 2026DAVE: A VLM Vision Encoder for Document Understanding and Web Agents
99. ICLR 2026DecompGAIL: Learning Realistic Traffic Behaviors with Decomposed Multi-Agent Generative Adversarial Imitation Learning
100. ICLR 2026DeepEyesV2: Toward Agentic Multimodal Model

常见问题

2023–2026 年四大会议一共有多少篇AI 智能体论文？

共 3,266 篇，按年份分别是 2023 年 170 篇、2024 年 329 篇、2025 年 784 篇、2026 年 1,983 篇。

NeurIPS 2026 有多少篇AI 智能体论文？

NeurIPS 2026 有 729 篇AI 智能体论文，上一届是 362 篇。

ICLR 2026 有多少篇AI 智能体论文？

ICLR 2026 有 500 篇AI 智能体论文，上一届是 204 篇。

ICML 2026 有多少篇AI 智能体论文？

ICML 2026 有 640 篇AI 智能体论文，上一届是 178 篇。

CVPR 2026 有多少篇AI 智能体论文？

CVPR 2026 有 114 篇AI 智能体论文，上一届是 40 篇。

哪个会议的AI 智能体论文最多？

NeurIPS，2023–2026 年共 1,317 篇。